sarvamai 0.1.22a4__py3-none-any.whl → 0.1.23a1__py3-none-any.whl

sarvamai/speech_to_text_streaming/__init__.py

@@ -2,18 +2,48 @@
 
 # isort: skip_file
 
-from .types import (
-    SpeechToTextStreamingFlushSignal,
-    SpeechToTextStreamingHighVadSensitivity,
-    SpeechToTextStreamingInputAudioCodec,
-    SpeechToTextStreamingLanguageCode,
-    SpeechToTextStreamingVadSignals,
-)
+import typing
+from importlib import import_module
+
+if typing.TYPE_CHECKING:
+    from .types import (
+        SpeechToTextStreamingFlushSignal,
+        SpeechToTextStreamingHighVadSensitivity,
+        SpeechToTextStreamingLanguageCode,
+        SpeechToTextStreamingVadSignals,
+    )
+_dynamic_imports: typing.Dict[str, str] = {
+    "SpeechToTextStreamingFlushSignal": ".types",
+    "SpeechToTextStreamingHighVadSensitivity": ".types",
+    "SpeechToTextStreamingLanguageCode": ".types",
+    "SpeechToTextStreamingVadSignals": ".types",
+}
+
+
+def __getattr__(attr_name: str) -> typing.Any:
+    module_name = _dynamic_imports.get(attr_name)
+    if module_name is None:
+        raise AttributeError(f"No {attr_name} found in _dynamic_imports for module name -> {__name__}")
+    try:
+        module = import_module(module_name, __package__)
+        if module_name == f".{attr_name}":
+            return module
+        else:
+            return getattr(module, attr_name)
+    except ImportError as e:
+        raise ImportError(f"Failed to import {attr_name} from {module_name}: {e}") from e
+    except AttributeError as e:
+        raise AttributeError(f"Failed to get {attr_name} from {module_name}: {e}") from e
+
+
+def __dir__():
+    lazy_attrs = list(_dynamic_imports.keys())
+    return sorted(lazy_attrs)
+
 
 __all__ = [
     "SpeechToTextStreamingFlushSignal",
     "SpeechToTextStreamingHighVadSensitivity",
-    "SpeechToTextStreamingInputAudioCodec",
     "SpeechToTextStreamingLanguageCode",
     "SpeechToTextStreamingVadSignals",
 ]

sarvamai/speech_to_text_streaming/client.py

@@ -13,7 +13,6 @@ from .raw_client import AsyncRawSpeechToTextStreamingClient, RawSpeechToTextStre
 from .socket_client import AsyncSpeechToTextStreamingSocketClient, SpeechToTextStreamingSocketClient
 from .types.speech_to_text_streaming_flush_signal import SpeechToTextStreamingFlushSignal
 from .types.speech_to_text_streaming_high_vad_sensitivity import SpeechToTextStreamingHighVadSensitivity
-from .types.speech_to_text_streaming_input_audio_codec import SpeechToTextStreamingInputAudioCodec
 from .types.speech_to_text_streaming_language_code import SpeechToTextStreamingLanguageCode
 from .types.speech_to_text_streaming_vad_signals import SpeechToTextStreamingVadSignals
 
@@ -44,7 +43,6 @@ class SpeechToTextStreamingClient:
         *,
         language_code: SpeechToTextStreamingLanguageCode,
         model: typing.Optional[typing.Literal["saarika:v2.5"]] = None,
-        input_audio_codec: typing.Optional[SpeechToTextStreamingInputAudioCodec] = None,
         sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextStreamingVadSignals] = None,
@@ -67,9 +65,6 @@ class SpeechToTextStreamingClient:
         model : typing.Optional[typing.Literal["saarika:v2.5"]]
             Speech to text model to use
 
-        input_audio_codec : typing.Optional[SpeechToTextStreamingInputAudioCodec]
-            Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
-
         sample_rate : typing.Optional[str]
             Audio sample rate for the WebSocket connection. When specified as a connection parameter, only 16kHz and 8kHz are supported. 8kHz is only available via this connection parameter. If not specified, defaults to 16kHz.
 
@@ -98,8 +93,6 @@ class SpeechToTextStreamingClient:
             query_params = query_params.add("language-code", language_code)
         if model is not None:
             query_params = query_params.add("model", model)
-        if input_audio_codec is not None:
-            query_params = query_params.add("input_audio_codec", input_audio_codec)
         if sample_rate is not None:
             query_params = query_params.add("sample_rate", sample_rate)
         if high_vad_sensitivity is not None:
@@ -153,7 +146,6 @@ class AsyncSpeechToTextStreamingClient:
         *,
         language_code: SpeechToTextStreamingLanguageCode,
         model: typing.Optional[typing.Literal["saarika:v2.5"]] = None,
-        input_audio_codec: typing.Optional[SpeechToTextStreamingInputAudioCodec] = None,
         sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextStreamingVadSignals] = None,
@@ -176,9 +168,6 @@ class AsyncSpeechToTextStreamingClient:
         model : typing.Optional[typing.Literal["saarika:v2.5"]]
             Speech to text model to use
 
-        input_audio_codec : typing.Optional[SpeechToTextStreamingInputAudioCodec]
-            Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
-
         sample_rate : typing.Optional[str]
             Audio sample rate for the WebSocket connection. When specified as a connection parameter, only 16kHz and 8kHz are supported. 8kHz is only available via this connection parameter. If not specified, defaults to 16kHz.
 
@@ -207,8 +196,6 @@ class AsyncSpeechToTextStreamingClient:
             query_params = query_params.add("language-code", language_code)
         if model is not None:
             query_params = query_params.add("model", model)
-        if input_audio_codec is not None:
-            query_params = query_params.add("input_audio_codec", input_audio_codec)
         if sample_rate is not None:
             query_params = query_params.add("sample_rate", sample_rate)
         if high_vad_sensitivity is not None:

sarvamai/speech_to_text_streaming/raw_client.py

@@ -12,7 +12,6 @@ from ..core.request_options import RequestOptions
 from .socket_client import AsyncSpeechToTextStreamingSocketClient, SpeechToTextStreamingSocketClient
 from .types.speech_to_text_streaming_flush_signal import SpeechToTextStreamingFlushSignal
 from .types.speech_to_text_streaming_high_vad_sensitivity import SpeechToTextStreamingHighVadSensitivity
-from .types.speech_to_text_streaming_input_audio_codec import SpeechToTextStreamingInputAudioCodec
 from .types.speech_to_text_streaming_language_code import SpeechToTextStreamingLanguageCode
 from .types.speech_to_text_streaming_vad_signals import SpeechToTextStreamingVadSignals
 
@@ -32,7 +31,6 @@ class RawSpeechToTextStreamingClient:
         *,
         language_code: SpeechToTextStreamingLanguageCode,
         model: typing.Optional[typing.Literal["saarika:v2.5"]] = None,
-        input_audio_codec: typing.Optional[SpeechToTextStreamingInputAudioCodec] = None,
         sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextStreamingVadSignals] = None,
@@ -55,9 +53,6 @@ class RawSpeechToTextStreamingClient:
         model : typing.Optional[typing.Literal["saarika:v2.5"]]
             Speech to text model to use
 
-        input_audio_codec : typing.Optional[SpeechToTextStreamingInputAudioCodec]
-            Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
-
         sample_rate : typing.Optional[str]
             Audio sample rate for the WebSocket connection. When specified as a connection parameter, only 16kHz and 8kHz are supported. 8kHz is only available via this connection parameter. If not specified, defaults to 16kHz.
 
@@ -86,8 +81,6 @@ class RawSpeechToTextStreamingClient:
             query_params = query_params.add("language-code", language_code)
         if model is not None:
             query_params = query_params.add("model", model)
-        if input_audio_codec is not None:
-            query_params = query_params.add("input_audio_codec", input_audio_codec)
         if sample_rate is not None:
             query_params = query_params.add("sample_rate", sample_rate)
         if high_vad_sensitivity is not None:
@@ -130,7 +123,6 @@ class AsyncRawSpeechToTextStreamingClient:
         *,
         language_code: SpeechToTextStreamingLanguageCode,
         model: typing.Optional[typing.Literal["saarika:v2.5"]] = None,
-        input_audio_codec: typing.Optional[SpeechToTextStreamingInputAudioCodec] = None,
         sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextStreamingVadSignals] = None,
@@ -153,9 +145,6 @@ class AsyncRawSpeechToTextStreamingClient:
         model : typing.Optional[typing.Literal["saarika:v2.5"]]
             Speech to text model to use
 
-        input_audio_codec : typing.Optional[SpeechToTextStreamingInputAudioCodec]
-            Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
-
         sample_rate : typing.Optional[str]
             Audio sample rate for the WebSocket connection. When specified as a connection parameter, only 16kHz and 8kHz are supported. 8kHz is only available via this connection parameter. If not specified, defaults to 16kHz.
 
@@ -184,8 +173,6 @@ class AsyncRawSpeechToTextStreamingClient:
             query_params = query_params.add("language-code", language_code)
         if model is not None:
             query_params = query_params.add("model", model)
-        if input_audio_codec is not None:
-            query_params = query_params.add("input_audio_codec", input_audio_codec)
         if sample_rate is not None:
             query_params = query_params.add("sample_rate", sample_rate)
         if high_vad_sensitivity is not None:

sarvamai/speech_to_text_streaming/types/__init__.py

@@ -2,16 +2,46 @@
 
 # isort: skip_file
 
-from .speech_to_text_streaming_flush_signal import SpeechToTextStreamingFlushSignal
-from .speech_to_text_streaming_high_vad_sensitivity import SpeechToTextStreamingHighVadSensitivity
-from .speech_to_text_streaming_input_audio_codec import SpeechToTextStreamingInputAudioCodec
-from .speech_to_text_streaming_language_code import SpeechToTextStreamingLanguageCode
-from .speech_to_text_streaming_vad_signals import SpeechToTextStreamingVadSignals
+import typing
+from importlib import import_module
+
+if typing.TYPE_CHECKING:
+    from .speech_to_text_streaming_flush_signal import SpeechToTextStreamingFlushSignal
+    from .speech_to_text_streaming_high_vad_sensitivity import SpeechToTextStreamingHighVadSensitivity
+    from .speech_to_text_streaming_language_code import SpeechToTextStreamingLanguageCode
+    from .speech_to_text_streaming_vad_signals import SpeechToTextStreamingVadSignals
+_dynamic_imports: typing.Dict[str, str] = {
+    "SpeechToTextStreamingFlushSignal": ".speech_to_text_streaming_flush_signal",
+    "SpeechToTextStreamingHighVadSensitivity": ".speech_to_text_streaming_high_vad_sensitivity",
+    "SpeechToTextStreamingLanguageCode": ".speech_to_text_streaming_language_code",
+    "SpeechToTextStreamingVadSignals": ".speech_to_text_streaming_vad_signals",
+}
+
+
+def __getattr__(attr_name: str) -> typing.Any:
+    module_name = _dynamic_imports.get(attr_name)
+    if module_name is None:
+        raise AttributeError(f"No {attr_name} found in _dynamic_imports for module name -> {__name__}")
+    try:
+        module = import_module(module_name, __package__)
+        if module_name == f".{attr_name}":
+            return module
+        else:
+            return getattr(module, attr_name)
+    except ImportError as e:
+        raise ImportError(f"Failed to import {attr_name} from {module_name}: {e}") from e
+    except AttributeError as e:
+        raise AttributeError(f"Failed to get {attr_name} from {module_name}: {e}") from e
+
+
+def __dir__():
+    lazy_attrs = list(_dynamic_imports.keys())
+    return sorted(lazy_attrs)
+
 
 __all__ = [
     "SpeechToTextStreamingFlushSignal",
     "SpeechToTextStreamingHighVadSensitivity",
-    "SpeechToTextStreamingInputAudioCodec",
     "SpeechToTextStreamingLanguageCode",
     "SpeechToTextStreamingVadSignals",
 ]